Page: 1 2 3 4 5 6 7 8 9... 114
81 |
Язык описания проблемы и исследование его возможностей ... : Exploring Possibilities of Language for Describing the Problem ...
|
|
|
|
BASE
|
|
Show details
|
|
82 |
Breathing and Speech Planning in Spontaneous Speech Synthesis
|
|
|
|
BASE
|
|
Show details
|
|
83 |
Augmented Prompt Selection for Evaluation of Spontaneous Speech Synthesis
|
|
|
|
Abstract:
By definition, spontaneous speech is unscripted and created on the fly by the speaker. It is dramatically different from read speech, where the words are authored as text before they are spoken. Spontaneous speech is emergent and transient, whereas text read out loud is pre-planned. For this reason, it is unsuitable to evaluate the usability and appropriateness of spontaneous speech synthesis by having it read out written texts sampled from for example newspapers or books. Instead, we need to use transcriptions of speech as the target - something that is much less readily available. In this paper, we introduce Starmap, a tool allowing developers to select a varied, representative set of utterances from a spoken genre, to be used for evaluation of TTS for a given domain. The selection can be done from any speech recording, without the need for transcription. The tool uses interactive visualisation of prosodic features with t-SNE, along with a tree-based algorithm to guide the user through thousands of utterances and ensure coverage of a variety of prompts. A listening test has shown that with a selection of genre-specific utterances, it is possible to show significant differences across genres between two synthetic voices built from spontaneous speech. ; QC 20201020
|
|
Keyword:
Engineering and Technology; evaluation; human-in-the-loop; intelligence augmentation; spontaneous speech synthesis; Teknik och teknologier
|
|
URL: http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-283733
|
|
BASE
|
|
Hide details
|
|
84 |
Adaptive 3D Model-Based Facial Expression Synthesis and Pose Frontalization
|
|
|
|
In: Sensors ; Volume 20 ; Issue 9 (2020)
|
|
BASE
|
|
Show details
|
|
85 |
Non-Contact Speech Recovery Technology Using a 24 GHz Portable Auditory Radar and Webcam
|
|
|
|
In: Remote Sensing ; Volume 12 ; Issue 4 (2020)
|
|
BASE
|
|
Show details
|
|
86 |
Editorial for Special Issue “IberSPEECH2018: Speech and Language Technologies for Iberian Languages”
|
|
|
|
In: Applied Sciences ; Volume 10 ; Issue 1 (2020)
|
|
BASE
|
|
Show details
|
|
87 |
Semantic Deep Face Models
|
|
|
|
In: 2020 International Conference on 3D Vision (3DV) (2020)
|
|
BASE
|
|
Show details
|
|
88 |
MacArthur-Bates Communicative Developmental Inventories (CDI): A Research Synthesis Evaluating Children at 2-36 months
|
|
|
|
In: MA in Linguistics Final Projects (2020)
|
|
BASE
|
|
Show details
|
|
89 |
Controlling the voice quality dimension of prosody in synthetic speech using an acoustic glottal model
|
|
MURPHY, ANDREW. - : Trinity College Dublin. School of Linguistic Speech & Comm Sci. C.L.C.S., 2020
|
|
BASE
|
|
Show details
|
|
90 |
Eco‑evo‑devo and iterated learning : towards an integrated approach in the light of niche construction
|
|
|
|
BASE
|
|
Show details
|
|
91 |
Identification of Novel Modifiers of RAN Translation at FMR1 and C9ORF72
|
|
|
|
BASE
|
|
Show details
|
|
92 |
How the Reading for Understanding Initiative’s Research Complicates the Simple View of Reading Invoked in the Science of Reading
|
|
|
|
BASE
|
|
Show details
|
|
93 |
Challenges and Perspectives on Real-time Singing Voice Synthesis
|
|
|
|
In: Revista de Informática Teórica e Aplicada; v. 27, n. 4 (2020); 118-126 ; 21752745 ; 01034308 (2020)
|
|
BASE
|
|
Show details
|
|
95 |
Technology-mediated task-based language teaching: A qualitative research synthesis
|
|
Chong, Sin Wang; Reinders, Hayo. - : University of Hawaii National Foreign Language Resource Center, 2020. : Center for Language & Technology, 2020. : (co-sponsored by Center for Open Educational Resources and Language Learning, University of Texas at Austin), 2020
|
|
BASE
|
|
Show details
|
|
96 |
Diversity and Inclusion in Psychiatry: The Pursuit of Health Equity
|
|
|
|
In: Focus (Am Psychiatr Publ) (2020)
|
|
BASE
|
|
Show details
|
|
97 |
Phonetic convergence in the shadowing for natural and synthesized speech in Polish
|
|
|
|
In: Lingua Posnaniensis, Vol 62, Iss 2, Pp 7-17 (2020) (2020)
|
|
BASE
|
|
Show details
|
|
98 |
F0 modeling using DNN for Arabic parametric speech synthesis
|
|
|
|
In: INNSBDDL 2019 - INNS Big Data and Deep Learning ; https://hal.inria.fr/hal-02177496 ; INNSBDDL 2019 - INNS Big Data and Deep Learning, Apr 2019, Sestri Levante, Italy (2019)
|
|
BASE
|
|
Show details
|
|
99 |
Annotation and data-driven synthesis of facial expressions of French sign language ; Annotation et synthèse basée données des expressions faciales de la Langue des Signes Française
|
|
|
|
In: https://hal.archives-ouvertes.fr/tel-03080311 ; Computer science. Université Bretagne-Sud, 2019. English (2019)
|
|
BASE
|
|
Show details
|
|
100 |
Text-to-Speech Synthesis Using Found Data for Low-Resource Languages
|
|
|
|
BASE
|
|
Show details
|
|
Page: 1 2 3 4 5 6 7 8 9... 114
|
|